More researches aimed to acquire relationships between verbs or verb phrases indicating the causal event and effect one. Inui used explicit connective marker tame, such as “because”, “since”, “as the result”, etc., to discover causal relation from two adjacent sentences (Inui, 2005). In this work, Inui further classified the causal relation into four subtypes mainly based on event-agents’ volitionality, which is learned by the Support Vector Machine (SVM) model. The result reported was satisfactory with the precision of about 85%. (Pechsiri, 2007) used verb-pair rules learnt by two different machine learning techniques (NB and SVM) to identify causality from multiple Elementary Discourse Units. The average precision of both models exceed 80%.